{"id":"W3163203195","doi":"10.1016/j.bone.2021.116017","title":"Feasibility of a generalized convolutional neural network for automated identification of vertebral compression fractures: The Manitoba Bone Mineral Density Registry","year":2021,"lang":"en","type":"article","venue":"Bone","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Convolutional neural network; Bone mineral; Artificial intelligence; Receiver operating characteristic; Pattern recognition (psychology); Dual energy; Sensitivity (control systems); Computer science; Nuclear medicine; Mathematics; Medicine; Machine learning; Osteoporosis; Engineering; Pathology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002525599,0.00009049987,0.000262967,0.00001988047,0.00006592204,0.00001347051,0.00008474751,0.00006201759,0.00002935122],"category_scores_gemma":[0.0001746325,0.00007000699,0.0001394053,0.0001620237,0.00008866764,0.00004094643,0.00002696882,0.00009923746,0.000001135455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002650942,"about_ca_system_score_gemma":0.00002760756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007422871,"about_ca_topic_score_gemma":0.00005627837,"domain_scores_codex":[0.9990278,0.00007225895,0.0004066924,0.0001431541,0.0002065289,0.0001435047],"domain_scores_gemma":[0.9992768,0.00009518243,0.0001218427,0.0003014976,0.0001589135,0.00004580195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009758288,0.0002153476,0.03273079,0.000553204,0.0002769719,0.00001758955,0.0001658047,0.1959201,0.6721017,0.00042001,0.09596749,0.001533319],"study_design_scores_gemma":[0.0005984922,0.000004492068,0.09448109,0.00004337217,0.00009086931,0.00001293772,0.00003496021,0.893882,0.01030675,0.0003260373,0.0001434841,0.00007548549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9858813,0.001054257,0.01229322,0.0002515817,0.0002363586,0.0001122177,0.00004998925,0.0001031092,0.00001792831],"genre_scores_gemma":[0.9973857,0.00001578602,0.002054595,0.00005643484,0.0001395332,0.000009330593,0.0002230036,0.00000941735,0.0001061829],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6979619,"threshold_uncertainty_score":0.2854803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02117788505439838,"score_gpt":0.2740671608159846,"score_spread":0.2528892757615863,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}